JP2022523253A - 360 ° support for QCS scanners with mixed reality and machine learning technology - Google Patents

Abstract

Using optical sensors, displays, chatbots, cloud services, and processors operably connected to optical sensors and displays, combined reality and machine learning techniques provide 360 ° support to quality control scanners. The equipment, methods and non-temporary machine-readable media and processors provided identify and detect problems in the field equipment with optical sensors and guide the user to the location of the field equipment and the scanner section with the display to solve the problem. Receive diagnostic information from servers related to field equipment in industrial process control automation systems and connect to cloud servers for installation, commissioning, and annual maintenance contracts, as well as quality control systems to perform procedures or actions. Get the training module. [Selection diagram] Fig. 1

Description

This disclosure generally relates to autonomously operated industrial plants. Specifically, the present disclosure relates to a system and method for 360 ° support of a quality management system (QCS) scanner using mixed reality (MR) and machine learning techniques.

Installation, updating, and maintenance of the QCS scanner involves precise work by a series of operating procedures dealing with radiation sources, and no errors should occur, so skilled domain knowledge is required. People in the industry with expertise in QCS scanners are getting older and reaching retirement age. New TACs and service areas are facing difficulties in supporting QCS scanners due to capacity gaps and lack of expertise. In order to deal with the troubles of the QCS scanner, it is indispensable to narrow down the assumed problems accurately and to have domain knowledge to solve the assumed problems. Also, the time required to correct a problem may vary depending on the field of expertise. Training the QCS scanner requires a physical scanner for training and time in the physical environment.

The present disclosure provides systems and methods for 360 ° support of QCS scanners using mixed reality (MR) and machine learning techniques.

In a first embodiment, the device provides 360 ° support for a QCS scanner with mixed reality (MR) and machine learning techniques. The device includes an optical sensor, a display and a processor operably connected to the optical sensor and display. The processor receives diagnostic information from the server associated with the field equipment of the industrial process control automation system, identifies the field equipment problem based on this diagnostic information, and uses optical sensors to address the identified problem. Detects field equipment and uses the display to guide the user to the location of the field equipment and the scanner section related to the problem, and also uses the display to provide the necessary steps or actions to resolve the problem. do.

In a second embodiment, the method provides 360 ° support for a QCS scanner with mixed reality (MR) and machine learning techniques. The method was identified using optical sensors, a step of receiving diagnostic information from a server associated with the field equipment of an industrial process control automation system, a step of identifying problems in the field equipment based on this diagnostic information, and a step. Find the field device that corresponds to the problem, use the display to guide the user to the location of the field device related to the problem and the scanner section, and use the display to solve the problem. Includes steps to provide the necessary procedures or actions.

In a third embodiment, the non-temporary medium provides 360 ° support for a QCS scanner with mixed reality (MR) and machine learning techniques. The instructions are for one or more processors to receive diagnostic information from the server associated with the field equipment of the industrial process control automation system, and to identify problems in the field equipment based on this diagnostic information, and optical. Use the sensor to detect the field device that corresponds to the identified problem, and use the display to guide the user to the location of the field device related to the problem and the scanner section, and then the display. Use to perform steps and steps that provide the necessary steps or actions to resolve the problem.

Other technical features will be readily apparent to those skilled in the art from the figures, description, and claims below.

Here, for a more complete understanding of the present disclosure, reference is made to the following description along with the accompanying drawings.

FIG. 1 is a diagram showing an example of an industrial process control automation system according to the present disclosure.

FIG. 2 is a diagram showing an example device for 360 ° support of a QCS scanner by mixed reality (MR) and machine learning technology according to the present disclosure.

FIG. 3 is a diagram showing an example of a QCS scanner system for 360 ° support of a QCS scanner using mixed reality (MR) and machine learning technology according to the present disclosure.

FIG. 4 is a diagram showing a trouble-shooting method of an example QCS scanner by augmented reality, a chatbot, and a machine learning technique according to the embodiment of the present disclosure.

FIG. 5 is a diagram showing an example of QCS scanner training by augmented reality and chatbot technology according to an embodiment of the present disclosure.

FIG. 6 is a diagram showing installation, test run, and AMC of an example of a QCS scanner by augmented reality and chatbot technology according to the embodiment of the present disclosure.

FIG. 7A is a flow chart of an example relating to troubleshooting of the QCS scanner problem by the augmented reality, chatbot, and machine learning technique according to the embodiment of the present disclosure. FIG. 7B is a flow chart of an example relating to troubleshooting of the QCS scanner problem by the augmented reality, chatbot, and machine learning technique according to the embodiment of the present disclosure.

FIG. 8A is a flow chart of an example relating to installation and test run according to the embodiment of the present disclosure. FIG. 8B is a flow chart of an example relating to installation and test run according to the embodiment of the present disclosure.

FIGS. 1-8B discussed below, and the various embodiments used to illustrate the principles of the present disclosure in this patent document, are for illustration purposes only and limit the scope of the invention in any way. Should not be interpreted as what it does. Those skilled in the art will appreciate that the principles of the present disclosure can be practiced with some kind of well-placed device or system.

FIG. 1 shows an example of an industrial process control automation system 100 according to the present disclosure. As shown in FIG. 1, the system 100 includes various components that facilitate the manufacture or processing of at least one product or other material. For example, the system 100 can be used to facilitate control of components within one or more industrial plants. Each plant represents one or more processing equipment (or one or more parts thereof), such as one or more manufacturing equipment for producing at least one product or other material. In general, each plant can carry out one or more industrial processes and may be referred to individually or collectively as a process system. A process system generally refers to any system or part thereof that is configured to process one or more products or other materials in some way.

In FIG. 1, system 100 includes one or more sensors 102a and one or more actuators 102b. Sensors 102a and actuators 102b represent components within a process system capable of performing any of a wide variety of functions. For example, the sensor 102a can measure a wide variety of characteristics within the process system, such as pressure, temperature, flow rate, basis weight, moisture, ash content, calipers and the like. Further, the actuator 102b can also change a wide variety of characteristics of the process system. Each sensor 102a contains any suitable structure for measuring one or more properties within the process system. Each actuator 102b comprises any suitable structure for operating or influencing one or more conditions within the process system.

At least one network 104 is coupled to the sensor 102a and the actuator 102b. The network 104 facilitates interaction with the sensor 102a and the actuator 102b. For example, the network 104 can transmit measurement data from the sensor 102a and supply a control signal to the actuator 102b. The network 104 may indicate any suitable network or combination of networks. As a specific example, the network 104 can be an at least one Ethernet network, an electrical signal network (such as a HART or FOUNDATION FIELDBUS network), a pneumatic control signal network, or any other or new type (s) of networks. Can be equivalent.

The system 100 also includes various controllers 106. The controller 106 can be used within the system 100 to perform various functions in order to control one or more industrial processes. For example, the first set of controllers 106 can control the operation of one or more actuators 102b using measurements from one or more sensors 102a. A second set of controllers 106 can be used to optimize the control logic or other actions performed by the first set of controllers. A third set of controllers 106 can be used to perform new functions.

The controllers 106 are often arranged hierarchically in the system. For example, various controllers 106 can be used to control individual actuators, a set of actuators that form a machine, a set of machines that form a unit, a set of units that form a plant, and a set of plants that form a company. Is. A particular example of a hierarchical arrangement of controllers 106 is defined as a "paddie" model of process control. The various tier level controllers 106 can communicate via one or more networks 108, as well as associated switches, firewalls, and other components.

Each controller 106 includes any suitable structure for controlling one or more aspects of an industrial process. At least a portion of the controller 106 may be, for example, a proportional integral derivative (PID) controller, or a robust multivariable predictive control (RMPCT) controller or other type of controller that implements model predictive control or other advanced predictive control. Can indicate a multivariable controller. As a particular example, each controller 106 may correspond to a computing device running a real-time operating system, a WINDOWS operating system, or another operating system.

Operator access and interaction to the controller 106 and other components of the system 100 can be done via various operator consoles 110. Each operator console 110 can be used to provide information to and receive information from the operator. For example, each operator console 110 can provide the operator with information that identifies the current state of the industrial process, such as various process variables related to the industrial process and values of warnings, alarms, or other states. Further, each operator console 110 receives a set point or control mode for process variables controlled by the controller 106, or other information that modifies or acts on the way the controller 106 controls the industrial process. By doing so, you can receive information that affects how you control industrial processes.

The plurality of operator consoles 110 are grouped together and can be used in one or more control rooms 112. Each control room 112 may include any number of operator consoles 110 in any suitable arrangement. In some embodiments, a plurality of control chambers 112 are used to control an industrial plant, such as when each control chamber 112 includes an operator console 110 used to manage separate parts of the industrial plant. be able to.

Each operator console 110 includes any suitable structure for displaying information to the operator and interacting with the operator. For example, each operator console 110 is one or more processors, microprocessors, microcontrollers, field programmable gate arrays, application-specific integrated circuits, separate logic devices, or other processes or controls. The device 114 can be included. Further, each operator console 110 may include one or more memories 116 for storing instructions and data used, generated or collected by the processing device (s) 114. Each operator console 110 may also include one or more network interfaces 118 that support communication over at least one wired or wireless network, such as one or more Ethernet interfaces or wireless transceivers.

According to the present disclosure, techniques for 360 ° support of a QCS scanner using mixed reality (MR) and machine learning techniques are provided. One or more components of the system 100 (eg, the operator console 110) can be configured to perform one or more operations related to this technique.

FIG. 1 shows an example of an industrial process control automation system 100, which may be modified in various ways. For example, industrial control and automation systems are offered in a wide variety of configurations. The system 100 shown in FIG. 1 is intended to provide an example of an operating environment in which a pressure sensor can be used.

FIG. 2 shows an example device for 360 ° support of a QCS scanner using mixed reality (MR) and machine learning techniques according to the present disclosure. Specifically, FIG. 2 shows an exemplary computing device 200. In some embodiments, the computing device 200 can correspond to an operator station, server, remote server or device, or mobile device. The computing device 200 can be used to execute an application. For ease of explanation, the computing device 200 is described as being used in the system 100 of FIG. 1, but is this device related to any other suitable system (industrial process control automation)? It can be used with or without).

As seen in FIG. 2, the computing device 200 includes at least one processor 202, at least one storage device 204, at least one communication unit 206, and at least one input / output (I / O) unit 208. .. Each processor 202 is capable of executing instructions, such as instructions that can be loaded into memory 210. Each processor 202 is any suitable processing device such as one or more microprocessors, microcontrollers, digital signal processors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or individual circuits. ..

The memory 210 and the fixed storage 212 are arbitrary structures (data, program code, and / or other suitable information, temporary or permanent, etc.) configured to store information and assist in retrieval. This is an example of the storage device 204 corresponding to (s). The memory 210 may correspond to a random access memory, or any other suitable volatile or non-volatile storage device (s). The fixed storage 212 may include one or more components or devices that support long-term storage of data, such as read-only memory, hard drives, flash memory, or optical discs.

Communication unit 206 supports communication with other systems or devices. For example, the communication unit 206 may include at least one network interface card or wireless transceiver that supports communication over at least one wired or wireless network. The communication unit 206 can support communication over any suitable physical or wireless communication link (s).

The I / O unit 208 enables data input / output. For example, the I / O unit 208 can provide a connection for user input through a keyboard, mouse, keypad, touch screen, gesture control, image processing, or other suitable input device. In addition, the I / O unit 208 can transmit output to a display, printer or other suitable output device.

FIG. 3 is a diagram showing an example of a QCS scanner system 300 for 360 ° support of a QCS scanner 310 based on mixed reality (MR) and machine learning technology according to the present disclosure. The exemplary QCS scanner system 300 embodiments shown in FIG. 3 are for purposes of illustration only. FIG. 3 does not limit the scope of the present disclosure to any specific implementation.

The QCS Scanner System 300 provides a mixed reality (MR) (Augmented Reality (AR) / Virtual Reality (VR), machine learning, and chatbot solution that solves potential problems. By using MR, QCS By extending the physical conditions with interactive guidance for installing and updating the scanner, the trial run of the QCS system 300 will be safer and easier, and the usability will be improved.

The QCS system 300 integrates the diagnostic messages and failure information of the QCS scanner with the HoloLens 305. The QCS system 300 receives from a local / centralized solution center a troubleshooting chatbot and a solution that enables machine learning.

The QCS system creates virtual training for the QCS scanner in VR and AR, which reduces the total cost of training and physical hardware. The QCS system provides instructions on the safe handling of radiation sources in hazardous environments. The QCS system creates a copy of the scanner component, which provides detailed information about wiring details, device location identification information, checkpoints, and the like.

The AR solution provides an augmented physical scanner with real-time data for troubleshooting. The AR solution enhances the step-by-step setup for installing the QCS scanner. AR solutions can upload real-time scanner status.

Machine learning and chatbots 315 provide solutions for easy troubleshooting based on historical data through interactive live chat sessions between machines and expert chatters. Machine learning and chatbots 315 can record problems and their resolution steps for future use.

VR solutions can provide alternatives for practicing QCS scanner installation and commissioning without access to expensive physical components. The VR solution can simulate a QCS scanner scenario such as actual system training for troubleshooting, and can display the live status and hints of the QCS system.

The phrase "360 ° support" in a QCS scanner refers to the overall support of a QCS scanner. The four main modules of the QCS scanner regarding support are: Module 1: Troubleshooting problems with the QCS scanner during processing; Module 2: Training; Module 3: Installation and commissioning of the QCS scanner; and Module 4: Annual maintenance / regular check. All modules that describe QCS scanner support require different technology / technology combinations and approaches to achieve process standardized, timed, predictable and reliable.

FIG. 4 shows an example of a QCS scanner trouble-shooting method 400 using augmented reality, a chatbot, and a machine learning technique according to an embodiment of the present disclosure. The embodiment of the exemplary QCS Scanner Troubleshooting Method 400 shown in FIG. 4 is for illustrative purposes only. FIG. 4 does not limit the scope of the present disclosure to any particular implementation.

The QCS troubleshooting method 400 includes HoloLens 405, chatbot 410, problem identification 415, eDocmation 420, machine learning server 425, and expert support 430. HoloLens 405 is designed to identify QCS scanners and their internal components, virtual wiring layouts, connection identification information, scanner machine component identification information, etc., based on a scanner version that can also video stream the scanner for remote assistants. It is a holographic computer.

The chatbot 410 can provide an interactive voice-based chatbot technique that accepts voice input from the user and provides the output needed to guide the user to perform the required operation.

Problem identification 415 involves integrating HoloLens with a QCS server and a QCS scanner to provide scanner-related diagnostics based on diagnostic information. HoloLens can guide the user to a problem location or scanner component and provide procedures or actions to be taken to solve the problem.

The eDocuation 420 allows HoloLens to identify objects and provide information about the objects, such as wiring diagrams, machine connections, test points, and so on. eDocnation can also use chatbots to receive documents requested by users, reducing search time and data availability and improving the user experience. HoloLens can identify objects related to field equipment. The user can provide commands that HoloLens receives from an audio sensor or from an external device. HoloLens displays the document that corresponds to the document type of the identified object.

The machine learning server 425 is a cloud service provided to solve a problem based on the importance of the problem. Users connect to the machine learning server with a chatbot, request a solution, provide a solution based on similar problems in the past, and the system will have a more reliable and accurate solution in the future. Can record the steps taken to solve the current problem.

Expert Support 430 is used when the machine learning server is unable to solve the problem and the user needs expert assistance. HoloLens can request to connect to an expert available for machine learning servers. When you connect with an expert, they can explain the problem while actually showing it to solve the problem. Once the problem is resolved, the machine learning server can record the steps taken to resolve the problem.

FIG. 5 shows an example QCS scanner training system 500 based on augmented reality and chatbot techniques according to an embodiment of the present disclosure. The exemplary QCS Scanner Training 500 embodiment shown in FIG. 5 is for illustrative purposes only. FIG. 5 does not limit the scope of the present disclosure to any particular implementation.

The QCS Training 500 includes a HoloLens 505 with a chatbot 510, a cloud-based training manual with a cloud-based eDocment & Video Training 515 and a cloud-based virtual training module 520, as well as a virtual training 525.

The wearable or HoloLens 505 is a holographic computer that can simulate a QCS scanner in a virtual world that allows the virtual QCS scanner to form images. HoloLens 505 shows how a physical scanner looks and is virtually imaged to assist user learning of various components (sensors, mechanisms, hardware and software configurations, etc.) before running the actual scanner. Can show the internal parts that can be made.

The chatbot 510 is an interactive voice-based chatbot capable of accepting voice input from the user and providing the output necessary to guide the user to perform the necessary action to solve the problem.

The cloud-based eDocument & Video Training 515 covers the basic introduction and industrial use of QCS scanners. The cloud-based virtual training module 520 can provide knowledge about QCS scanners, sensors, mechanisms, hardware and software configurations, handling, services, and troubleshooting. Examples of training modules may include installation and test run modules 530, QCS application modules 535, troubleshooting modules 540, AMC & service modules 545 and the like.

The virtual training 525 is used when the user wears HoloLens and connects to the cloud-based training module. HoloLens selects the persona for the training module. Virtual reality allows chatbot users to test run, troubleshoot, and view plant scenario usage without having to use or access a physical scanner.

FIG. 6 shows an example installation, test run and AMC system 600 of an augmented reality and chatbot technique QCS scanner according to an embodiment of the present disclosure. The embodiment of the exemplary system 600 of the QCS scanner shown in FIG. 6 is for illustrative purposes only. FIG. 6 does not limit the scope of the present disclosure to any particular implementation.

System 600 of the QCS scanner includes installation, test run, and annual maintenance contract (AMC). System 600 includes HoloLens 605 with chatbot 610, cloud-based installation & AMC module 615, installation and test run 620, expert support 625, and AMC activity 630.

The HoloLens 605 is a holographic computer created to locate the site and provide prerequisites and confirmations for installing a QCS scanner. The HoloLens 605 can use augmented reality to guide the user during the installation and commissioning of QCS scanners, various sensors, and internal components. At HoloLens, you can get expert advice with a remote assistant.

The chatbot 610 is an interactive voice-based chatbot capable of accepting voice input from the user and providing the output necessary to guide the user to perform the necessary action to solve the problem.

The cloud-based installation & AMC module 615 includes various modules that can be accessed based on requirements from the cloud, which are broadly categorized into submodules. Submodules include installation module 635, QCS sensor module 640, QCS software installation and configuration module 645, AMC activity for QCS scanner module 650, etc. to support various versions of QCS scanners.

Installation and test run 620 includes HoloLens connecting to cloud services. HoloLens selects QCS scanner versions and sensors that can be used for test runs. Installation and test run 620 can guide HoloLens in a step-by-step procedure for test run of the QCS scanner, as well as software installation and configuration for full-scale launch of the QCS scanner.

Expert Support 625 can provide HoloLens with expert assistance in installation, test run, and AMC if the user does not understand part of the process or problems with the QCS scanner. HoloLens can connect with experts and provide a QCS scanner look when talking to HoloLens users. Experts can control HoloLens to show the components to the user. In this way, the expert can better explain the steps or procedures to solve the problem.

AMC activity 630 is based on a customer recording system that allows the creation of AMC checklists. The AMC activity 630 can guide the user to perform an ACM activity that controls HoloLens and allows the technician to collect reports on the activity and comments in action. HoloLens can generate a final report of AMC activity on customer and user records.

7A and 7B show exemplary methods 700, 701 for troubleshooting the QCS scanner problem with augmented reality, chatbots and machine learning techniques according to embodiments of the present disclosure. For example, the methods described in FIGS. 7A and 7B can be performed in conjunction with the computing device 200 of FIG.

At operation 705, the computing device 200 can detect a problem with the QCS scanner. In some embodiments, problem detection by the computing device 200 comprises receiving diagnostic information from a server associated with a field device such as a QCS scanner in an industrial process control automation system. Field equipment problems include malfunctions that cause field equipment to malfunction with proper operating requirements.

At operation 710, the computing device 200 can connect to the QCS server and receive a list of possible problems. The list of possible problems may include typical problems identified by the particular machine itself or from a commonly used malfunction list by device type.

At operation 715, the computing device 200 can receive a voice command to select an expected problem from the assumed problem list. The possible problem list can be displayed on the display or provided to the user as audio output. In some embodiments, the computing device 200 can identify a field device problem based on diagnostic information.

At operation 720, the computing device 200 can capture a QCS scanner using an optical sensor on HoloLens. The computing device 200 can detect the field device corresponding to the problem identified by the optical sensor. Once the field equipment is captured and detected, the computing device can identify specific components that correspond to the identified problem.

At operation 725, the computing device 200 can display instructions on the HoloLens display that corresponds to the components associated with the possible problems of the QCS scanner. The computing device 200 can use the display to guide the user to the location of the field device and the scanner unit involved in the problem.

At operation 730, the computing device 200 can receive by voice command a request for relevant documents and procedures to solve the problem. The computing device 200 can provide the necessary procedures or measures to solve the problem. The required procedure or procedure can be shown on the display. Certain components related to the steps of the procedure may be highlighted or recorded on the display along with the relevant documents. The computing device 200 can display the relevant document on the display away from the highlighted or recorded components.

At operation 735, the computing device 200 can determine if the problem has been resolved. Once the problem is resolved, the computing device 200 proceeds to operation 780. If the problem is not resolved, the computing device 200 proceeds to operation 740.

At operation 740, the computing device 200 can detect that the problem has not been resolved. The computing device 200 can receive operation data from the QCS server and determine that the field device is still not operating efficiently.

At operation 745, the computing device 200 can connect HoloLens to a cloud-based service on a machine learning server to enhance support for possible problems. Cloud-based services can be directly associated with specific components.

At operation 750, the computing device 200 can use the chatbot service to provide detailed information about the problem to the machine learning server. The detailed information can include the information of the field device from the QCS server together with the information taken in by the computing device 200. Information captured by computing devices includes live feeds or frames captured from optical sensors, audio captured by users, frames captured from the display of processes used to fix problems, and so on. obtain.

At operation 755, the computing device 200 can receive a solution related to the problem based on past history from the machine learning server. Past history includes problems solved from field equipment in the past, as well as other field equipment of the same type. The machine learning server can provide the optimal solution based on all the input data or various alternative options.

At operation 760, the computing device 200 can determine if the problem has been resolved. Once the problem is resolved, the computing device 200 proceeds to operation 780. If the problem is not resolved, the computing device 200 proceeds to operation 765.

At operation 765, the computer device 200 can request the machine learning server to connect to an expert in the subject area of the Technical Support Center (TAC) Center. The subject matter expert may be someone who has experience using a particular type of field equipment or who has addressed a particular problem.

At operation 770, the computing device 200 can provide the subject matter expert with detailed information about the problem and a live feed from the HoloLens optical sensor. Subject experts can connect live or send relevant information related to field equipment.

At operation 775, the computing device 200 can receive an expert report on solving the problem from an expert in the subject area. The expert report may contain step-by-step instructions for resolving the problem. At each step, it is also possible to highlight the various components corresponding to each step, or to attach a specific marker to the display.

At operation 780, the computing device 200 can record the problem type and the solution procedure in the machine learning server. The problem type and solution procedure may be related to a specific component or a collection of components, or may be related to a malfunction of a field device. At operation 785, the computing device 200 can determine that the problem has been resolved.

7A and 7B show examples of 360 ° support methods 700,701 for QCS scanners using mixed reality (MR) and machine learning techniques, although various changes can be made to FIG. For example, the various steps shown in FIG. 7 may overlap, occur in parallel, may occur in different orders, or may occur any number of times.

8A and 8B show a flow chart of an example relating to the installation and test run according to the embodiment of the present disclosure. For example, the methods described in FIGS. 8A and 8B are feasible in conjunction with the installation, test run and AMC system 600 of FIG.

In operation 805, the installation, test run and AMC system 600 can start the installation, test run and AMC system of the QCS scanner.

In operation 810, the installation, test run and AMC system 600 can connect to the cloud server to obtain personas for installation, test run and AMC from the wearable device.

In operation 815, the installation, test run and AMC system 600 can determine whether the installation and test run persona is selected.

In operation 820, the installation, test run and AMC system 600 can use voice commands for wearable devices to request the cloud server for the installation modules required by the supported version of the QCS scanner.

At operation 825, the installation, test run and AMC system 600 can obtain a list of supported hardware and software installations for QCS scanners and sensors.

In operation 830, the installation, commissioning and AMC system 600 requests the cloud server for required modules, including a QCS scanner installation module, a QCS sensor module, and a QCS software installation configuration module, using voice commands for wearables. Can be done.

At operation 835, the installation, commissioning and AMC system 600 can receive from the cloud server a series of steps required to perform the installation and commissioning of the QCS scanner on the wearable device.

In operation 840, the installation, test run and AMC system 600 can perform installation and test run from the instructions and evaluate the results on the wearable device.

At operation 845, the installation, test run and AMC system 600 can determine if the user can execute an instruction or a set of instructions.

At operation 850, the installation, test run and AMC system 600 can be assisted by subject matter experts to solve the problem through interactive chat in live video.

In operation 855, the installation, test run and AMC system 600 can select the AMC module.

In operation 860, the installation, test run and AMC system 600 can request AMC records and checklists from the cloud server based on the version of the QCS scanner using voice commands for wearable devices.

At operation 865, the installation, test run and AMC system 600 can receive a list checklist of QCS scanners selected for AMC.

At operation 870, the installation, test run and AMC system 600 can receive from the cloud server a series of steps required to perform on the AMC QCS scanner of the wearable device.

At operation 875, the installation, test run and AMC system 600 can perform AMC from this instruction and evaluate the results on the wearable device.

In operation 880, the installation, test run and AMC system 600 can determine if the user can execute an instruction or a set of instructions.

At operation 885, the installation, test run and AMC system 600 can be assisted by subject matter experts to solve problems through interactive chat in live video.

8A and 8B show examples of 360 ° support methods 800,801 for mixed reality (MR) and machine learning techniques, but various changes can be made to FIG. For example, the various steps shown in FIG. 8 may overlap, occur in parallel, may occur in different orders, or may occur any number of times.

It would be helpful to explain the definitions of specific words and phrases used throughout this patent document. The phrases "transmit", "receive", "communicate", and their derivatives include the meanings of both direct and indirect communication. The terms "include" and "comprise" and their derivatives mean non-limiting inclusion. The term "or" is inclusive and means "and / or". The phrase "associate with" and its derivatives are contained, contained, interconnected, included, contained within, interconnected, interconnected. Includes being communicable, coordinating, alternating, paralleling, being in close proximity, being interconnected, having, having attributes, having relationships with each other, etc. It may mean. When used with a list of items, the phrase "at least one of" may be used in various combinations of one or more of the items listed, only one item in the list. Means that it can be needed. For example, "at least one of A, B, and C" includes any of the combinations A, B, C, A and B, A and C, B and C, and A and B and C.

Although the present disclosure has described specific embodiments and generally relevant methods, modifications and changes to these embodiments and methods will be apparent to those of skill in the art. Accordingly, the above description of the exemplary embodiments does not define or limit the present disclosure. Other modifications, substitutions, and modifications may also be made without departing from the spirit and scope of the present disclosure as defined by the appended claims.

Claims (9)

A method of using a chatbot application for interactive communication between users, systems and remote support (700, 701).
The step (710) of receiving diagnostic information from the server (425) associated with the field equipment (310) of the industrial process control automation system (100), and
The step (715) of identifying the problem of the field device based on the diagnostic information,
The step (720) of using the optical sensor (102a) to detect the field device corresponding to the identified problem, and
A step (725) of using the display (208) to guide the user to the location of the field device and the scanner unit involved in the problem.
Step (730), which uses the display to provide the necessary steps or actions to solve the problem.
Steps to connect to the user on the cloud server (430) and obtain the installation, test run, and annual maintenance contract (AMC), as well as the quality management system (QCS) training module (530-545) according to the selected persona. 810) and methods (700, 701). The method of claim 1, wherein the field device is a quality management system (QCS) scanner. If the required procedure or procedure does not solve the problem, then the method is:
The step (750) of providing detailed information on the problem to the cloud-based service on the machine learning server, and
The method of claim 1, further comprising receiving a related solution based on the past history of similar field equipment from the machine learning server (755). If the related solution does not solve the problem, then the method
The step (765) of requesting the machine learning server to connect to an expert in the target field, and
The method of claim 3, further comprising receiving an expert report for solving the problem from an expert in the subject area (775). The method of claim 4, wherein the method further comprises the step (770) of providing a live feed from the optical sensor to an expert in the subject area. The method is a step (775) of receiving instructions from an expert in the subject area to solve the problem, wherein the instructions include identification information of components in the live feed. (775) and
5. The method of claim 5, further comprising displaying a marker on the component identified in response to the particular operation in the instruction on a display. The method of claim 1, wherein the method further comprises a step (780) of recording a problem type and a solution procedure by a machine learning server based on the required procedure or action. It is a device (200)
With the optical sensor (102a)
Display (208) and
A device comprising a processor (202) operably connected to the optical sensor and the display, the processor (202) configured to perform the method of claims 1-7. (200). A non-transient machine-readable medium (212) encoded by an executable instruction, wherein the instruction causes one or more processors (202) to perform the method according to claims 1-7 at run time. , Non-temporary machine-readable medium (212).

Images